alt.freeweights.deepseek / DeepSeek-V3-0324
From: deepseek-ai <huggingface.co/deepseek-ai>Newsgroups: alt.freeweights.deepseekSubject:

DeepSeek-V3-0324

Date: 2026-11-14Commit: e9b33adSigned: 2DC28CC7B26A283B ✓

Text generation model with 684.5B parameters. Safetensors weights, 689 GB in all. Published by deepseek-ai under MIT.

684.5B params689GBDeepSeek-V3-0324safetensorspermissive
FactsParams684.5BSize689 GBFormatssafetensorsTasktext generationLicenseMITFrom sourcepermissive
$ fw get deepseek-ai/DeepSeek-V3-0324
# manifest sha256 7f685cc9501b… · 689 GB · 173 files
$ fw verify ./DeepSeek-V3-0324 deepseek-ai/DeepSeek-V3-0324
From sourceHosted (signed)deepseek-ai/DeepSeek-V3-0324Last check: 2026-11-14 21:14 UTC

Get help: custom fine-tune or private deploy. We review your setup before we quote.

Works with

Overview

Size
689 GB
Weights
689 GB (safetensors)
Parameters
684.5B
Formats
safetensors
Task
text generation
License
MIT (permissive)
Files
173, each with a sha256
Publisher
deepseek-ai
Added
2026-11-14
Section
alt.freeweights.deepseek
Lineage

Original release from the publisher.

Where these bytes come from
Publisher at the pinned commit→You

Sources are tried in order. A file counts only when its size and sha256 match the manifest. Sources are checked when you ask for them, not on a timer.

Sources
BadgeHostLast checkResult
From sourcehuggingface.co2026-11-14 21:14 UTCpassed

Model card

From the publisher at commit e9b33ad. Shown as plain text with links; images open at the publisher.

DeepSeek-V3-0324#

Image: DeepSeek-V3


Homepage Chat Hugging Face

Discord Wechat Twitter Follow

License

Features#

DeepSeek-V3-0324 demonstrates notable improvements over its predecessor, DeepSeek-V3, in several key aspects.

Image: Model Performance

Reasoning Capabilities#
  • Significant improvements in benchmark performance:
    • MMLU-Pro: 75.9 → 81.2 (+5.3)
    • GPQA: 59.1 → 68.4 (+9.3)
    • AIME: 39.6 → 59.4 (+19.8)
    • LiveCodeBench: 39.2 → 49.2 (+10.0)
Front-End Web Development#
  • Improved the executability of the code
  • More aesthetically pleasing web pages and game front-ends
Chinese Writing Proficiency#
  • Enhanced style and content quality:
    • Aligned with the R1 writing style
    • Better quality in medium-to-long-form writing
  • Feature Enhancements
    • Improved multi-turn interactive rewriting
    • Optimized translation quality and letter writing
Chinese Search Capabilities#
  • Enhanced report analysis requests with more detailed outputs
Function Calling Improvements#
  • Increased accuracy in Function Calling, fixing issues from previous V3 versions

Usage Recommendations#

System Prompt#

In the official DeepSeek web/app, we use the same system prompt with a specific date.

该助手为DeepSeek Chat,由深度求索公司创造。
今天是{current date}。

For example,

该助手为DeepSeek Chat,由深度求索公司创造。
今天是3月24日,星期一。
Temperature#

In our web and application environments, the temperature parameter $T_{model}$ is set to 0.3. Because many users use the default temperature 1.0 in API call, we have implemented an API temperature $T_{api}$ mapping mechanism that adjusts the input API temperature value of 1.0 to the most suitable model temperature setting of 0.3.

$$ T_{model} = T_{api} \times 0.3 \quad (0 \leq T_{api} \leq 1) $$

$$ T_{model} = T_{api} - 0.7 \quad (1 < T_{api} \leq 2) $$

Thus, if you call V3 via API, temperature 1.0 equals to the model temperature 0.3.

For file uploading, please follow the template to create prompts, where {file_name}, {file_content} and {question} are arguments.

file_template = \
"""[file name]: {file_name}
[file content begin]
{file_content}
[file content end]
{question}"""

For Web Search, {search_results}, {cur_date}, and {question} are arguments.

For Chinese query, we use the prompt:

search_answer_zh_template = \
'''# 以下内容是基于用户发送的消息的搜索结果:
{search_results}
在我给你的搜索结果中,每个结果都是[webpage X begin]...[webpage X end]格式的,X代表每篇文章的数字索引。请在适当的情况下在句子末尾引用上下文。请按照引用编号[citation:X]的格式在答案中对应部分引用上下文。如果一句话源自多个上下文,请列出所有相关的引用编号,例如[citation:3][citation:5],切记不要将引用集中在最后返回引用编号,而是在答案对应部分列出。
在回答时,请注意以下几点:
- 今天是{cur_date}。
- 并非搜索结果的所有内容都与用户的问题密切相关,你需要结合问题,对搜索结果进行甄别、筛选。
- 对于列举类的问题(如列举所有航班信息),尽量将答案控制在10个要点以内,并告诉用户可以查看搜索来源、获得完整信息。优先提供信息完整、最相关的列举项;如非必要,不要主动告诉用户搜索结果未提供的内容。
- 对于创作类的问题(如写论文),请务必在正文的段落中引用对应的参考编号,例如[citation:3][citation:5],不能只在文章末尾引用。你需要解读并概括用户的题目要求,选择合适的格式,充分利用搜索结果并抽取重要信息,生成符合用户要求、极具思想深度、富有创造力与专业性的答案。你的创作篇幅需要尽可能延长,对于每一个要点的论述要推测用户的意图,给出尽可能多角度的回答要点,且务必信息量大、论述详尽。
- 如果回答很长,请尽量结构化、分段落总结。如果需要分点作答,尽量控制在5个点以内,并合并相关的内容。
- 对于客观类的问答,如果问题的答案非常简短,可以适当补充一到两句相关信息,以丰富内容。
- 你需要根据用户要求和回答内容选择合适、美观的回答格式,确保可读性强。
- 你的回答应该综合多个相关网页来回答,不能重复引用一个网页。
- 除非用户要求,否则你回答的语言需要和用户提问的语言保持一致。

# 用户消息为:
{question}'''

For English query, we use the prompt:

search_answer_en_template = \
'''# The following contents are the search results related to the user's message:
{search_results}
In the search results I provide to you, each result is formatted as [webpage X begin]...[webpage X end], where X represents the numerical index of each article. Please cite the context at the end of the relevant sentence when appropriate. Use the citation format [citation:X] in the corresponding part of your answer. If a sentence is derived from multiple contexts, list all relevant citation numbers, such as [citation:3][citation:5]. Be sure not to cluster all citations at the end; instead, include them in the corresponding parts of the answer.
When responding, please keep the following points in mind:
- Today is {cur_date}.
- Not all content in the search results is closely related to the user's question. You need to evaluate and filter the search results based on the question.
- For listing-type questions (e.g., listing all flight information), try to limit the answer to 10 key points and inform the user that they can refer to the search sources for complete information. Prioritize providing the most complete and relevant items in the list. Avoid mentioning content not provided in the search results unless necessary.
- For creative tasks (e.g., writing an essay), ensure that references are cited within the body of the text, such as [citation:3][citation:5], rather than only at the end of the text. You need to interpret and summarize the user's requirements, choose an appropriate format, fully utilize the search results, extract key information, and generate an answer that is insightful, creative, and professional. Extend the length of your response as much as possible, addressing each point in detail and from multiple perspectives, ensuring the content is rich and thorough.
- If the response is lengthy, structure it well and summarize it in paragraphs. If a point-by-point format is needed, try to limit it to 5 points and merge related content.
- For objective Q&A, if the answer is very brief, you may add one or two related sentences to enrich the content.
- Choose an appropriate and visually appealing format for your response based on the user's requirements and the content of the answer, ensuring strong readability.
- Your answer should synthesize information from multiple relevant webpages and avoid repeatedly citing the same webpage.
- Unless the user requests otherwise, your response should be in the same language as the user's question.

# The user's message is:
{question}'''

How to Run Locally#

The model structure of DeepSeek-V3-0324 is exactly the same as DeepSeek-V3. Please visit DeepSeek-V3 repo for more information about running this model locally.

This model supports features such as function calling, JSON output, and FIM completion. For instructions on how to construct prompts to use these features, please refer to DeepSeek-V2.5 repo.

NOTE: Hugging Face's Transformers has not been directly supported yet.

License#

This repository and the model weights are licensed under the MIT License.

Citation#

@misc{deepseekai2024deepseekv3technicalreport,
      title={DeepSeek-V3 Technical Report}, 
      author={DeepSeek-AI},
      year={2024},
      eprint={2412.19437},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2412.19437}, 
}

Contact#

If you have any questions, please raise an issue or contact us at service@deepseek.com.

Files

173 files · 689 GBWeights 689 GB (safetensors). Sizes and sha256 from the signed manifest.
Show all 173 files with their sha256
FileSizesha256
.gitattributes1.52 KB11ad7efa24975ee4b0c3c3a38ed18737f0658a5f75a0a96787b576a78a023361
LICENSE1.06 KB1c8f573e830ca9b3ebfeb7ace1823146e22b66f99ee223840e7637c9e745e1c7
README.md10.7 KB598c401e426453f87161fb90a7c28a62e395b023a683c43d0793bf0d45753ba9
config.json1.66 KB79ddea672a62e95d3f0be27be434375538e1988975971cffcf87c96c1de84a65
configuration_deepseek.py9.90 KBd5126f7a82eaa5fe10c294af7a8f02d59e7145c2dc8837b83ae338c1b72001d2
figures/0324_comparison.png292 KB7212ae57a3a299c664858e74db102ef70daab173c00a3fa4913deb9d3cddb370
model-00001-of-000163.safetensors5.23 GB134f51f4642dde3f3d63aacc8e4605e6355d27aceb4ee1a1f914e30464623f10
model-00002-of-000163.safetensors4.30 GB400b76ca459923cc0c710ca51e05c8aa6167f595af208c15107800394a66a504
model-00003-of-000163.safetensors4.30 GB1e0192d491a2cad015aed550f8c072c69dbea143e9f55074b4f5b513c0633026
model-00004-of-000163.safetensors4.30 GB6f8ca069011e31d606dee00db53b3dc5160834327f17102353f28cad3b387587
model-00005-of-000163.safetensors4.30 GB1973c53f492006ff0eb70d677ebfa42bc40d2cafc1e15e64eb600765bfe7b7c1
model-00006-of-000163.safetensors4.37 GB2250eb7be1d22707f2effe99562de640b55980c2913e0640fa24d571cdfed642
model-00007-of-000163.safetensors4.31 GB8632d0847cd3082d9b66edefcc72d80c717b3fe4535b3d68b808da3c8806bceb
model-00008-of-000163.safetensors4.30 GB85daa7fd14a621a084a16c2669a8b95bad9173353fa9ec2f0fd6be6726866a32
model-00009-of-000163.safetensors4.30 GBb55f6542adae951b242e8e8444567fca59f6c2c380322a51abd49341871863be
model-00010-of-000163.safetensors4.30 GB0317ba8c85441b4f3d0134d2d43a1535e073250ba223283ceffc46bdef5dd77b
model-00011-of-000163.safetensors4.30 GBc5291900ff83cdf2786565e133d6b792313526df8e5cc17c120e0386426e66d7
model-00012-of-000163.safetensors1.32 GB1596e384e28712a7da32481b414ad2f9d5205b7d914066aaa77861f52218e3e3
model-00013-of-000163.safetensors4.30 GB0b5b8ac70defdc5393f02525d88ba2eb145f51ce9b2a11637de11b522d7c0da1
model-00014-of-000163.safetensors4.30 GBdf727377a86d6bc8b3ae4ac3f4fb0937c5476fb8b19edd28c0924d016e7199f4
model-00015-of-000163.safetensors4.30 GBae96924ba8d4f9e56221316ac185b1b5655ad08fd6abb425288d70f8e867d3a2
model-00016-of-000163.safetensors4.30 GB506313cbaf4ed810cf5d104229fdbc4e19cde2b12cea9e55e9550131b171409e
model-00017-of-000163.safetensors4.30 GBd396bde693edd1001be8440865e2c61b121d0cad562596e19ca01bf29dabcca4
model-00018-of-000163.safetensors4.30 GB4ebc50b2e0e220583a2597770d94f1a6c3e87be325470d0f4a15984bab424354
model-00019-of-000163.safetensors4.30 GB0a9d59229d198ee0b4966834d17d61811e8afe998e7634c87e643f51bc866d75
model-00020-of-000163.safetensors4.30 GBac27c6cbc27131a06e0562c14292ff26d17c62b156a068e4a41c9f56fead89f7
model-00021-of-000163.safetensors4.30 GB8afd4121eeb804b11838f51f4b49598d0e66bafe40d70a2def88698901a595d6
model-00022-of-000163.safetensors4.30 GBd6e5d4ea01bc15edb85b06f7d0ea9a41acf2efe18dd7c6bf1d85ddf2c4074fc0
model-00023-of-000163.safetensors4.30 GB9406624825565d25194fdf9462b397b5acba0bcab3bf1bdf9601952280945269
model-00024-of-000163.safetensors4.30 GB488969a9e8a378b243594f86144827dfb4c8549b3c6d719e21572a2306e742b4
model-00025-of-000163.safetensors4.30 GB450cc3f29910ee8d38ac5a5ec39901f83f63920bbc4d15175e5f5e58119dff29
model-00026-of-000163.safetensors4.30 GBbdfe115c31c700af118ca1f2f3cfb121c1d60e40404a688d63b686e8b54eacb7
model-00027-of-000163.safetensors4.30 GB13e981a9bdc7527d1d496ebe47456c7edd81d843c8125597d5ee640f18d65413
model-00028-of-000163.safetensors4.30 GBd767507070d19fa2736474f701a58317a9584e32df6d9bd010611f939c86049d
model-00029-of-000163.safetensors4.30 GB11b1ef947996f5426c462156be33547dbf1b08d8a12eca063d27889553e77470
model-00030-of-000163.safetensors4.30 GB6ff7740ee8707ad1e058634afd4d8c525cc2dbd13d81be8bd3ebbe2d999b9461
model-00031-of-000163.safetensors4.30 GB07afa8b68a432adc61b74f5649265bb656efae1ffcd6da6f23549f6b53a2093a
model-00032-of-000163.safetensors4.30 GB361f93b0bcbf04a2d5c99f2265d74c16d2ac6606fea1322633be0d4c578f93ac
model-00033-of-000163.safetensors4.30 GBd5cd3a3bd61d43a159b186554e0d652d90ef80355a4d64cdfab2f09c59586ea1
model-00034-of-000163.safetensors1.75 GBdf4c5f0efee23e96b0420e25a63e266acffba55a72c4dbb23efcaecaee279461
model-00035-of-000163.safetensors4.30 GB59907496ec35f620146f7e2a771acbae6315b73beb7c9b4484791a5769e92720
model-00036-of-000163.safetensors4.30 GB816a8da951743290c6cc77ee584023fd9063447256abef3937e9d73aed442e40
model-00037-of-000163.safetensors4.30 GB03da5c0e525f134c3fb902409a9e737608c38a30710ed489a8e6627b511a25e1
model-00038-of-000163.safetensors4.30 GBc0e6e082c73bdba9c830cfe08ec9f6424cd83296cae517dfab2338270a848334
model-00039-of-000163.safetensors4.30 GBa8dba03ca01e579f57e83906aed8aa9f4cd8205f6d32b9888dee455a64896b34
model-00040-of-000163.safetensors4.30 GB2ebb24adff0b0955375de7ffa071a27381df5dfcef8273b634de47f43199b0e1
model-00041-of-000163.safetensors4.30 GB5a50db6c7cb71fe98b0509453599af97096831686894e862dd0e780f10386882
model-00042-of-000163.safetensors4.30 GB9666e834327b2fdc9cb3be9954eda58754c7415dd63ccce449ec1e5e492a5924
model-00043-of-000163.safetensors4.30 GBdda5691da3edae3b462c90722d82a345dbb5713ea7d0739c865b09aea593f601
model-00044-of-000163.safetensors4.30 GB743f7e5979b3bd6512f3eccedb3665ae2ba0911b427041d7400f898c031b13cb
model-00045-of-000163.safetensors4.30 GB929fa255d58727dae32f88ff5323cb45a9a898e864926341cecac859570114b8
model-00046-of-000163.safetensors4.30 GB3ae202c6641bad95cc6b5c9e75b4410470ed6ca63941572342318045972062fa
model-00047-of-000163.safetensors4.30 GBe3c9d4d06ab071d1052790d8a401c56eef5571cb2b690778dab2e66e81242812
model-00048-of-000163.safetensors4.30 GBb5dbbd1df4a075642f11f88308c5648e90bafbaf74bece18ae5b77f17f36d905
model-00049-of-000163.safetensors4.30 GB308925e3cd15b67b74e6a3422d3e4667f31fc27eaa8e8669eb439942ee62159d
model-00050-of-000163.safetensors4.30 GBb97524be8e16c10e5e3eb8f527f1b7e5fddd11c671b884a3e4c74df3991345fb
model-00051-of-000163.safetensors4.30 GB68fa813be7c3644a99d38a6fcb8d928e32a9691d1af1b51cbd0ce0afff240aeb
model-00052-of-000163.safetensors4.30 GB806f360b5b46495a4f767a4aa9e4a83fceb6cf61415e3b418b714a3dd1411c68
model-00053-of-000163.safetensors4.30 GB9a8867bd41c3afe375ebcedf39a9e2b3793f69e4eeafdcdca8ca8ce9e2f810bd
model-00054-of-000163.safetensors4.30 GB274d3dd5e855ea3d06f29092c836c7bc628e22ba99fb6ee05520fb2da4b581e1
model-00055-of-000163.safetensors4.30 GBc4978652ad095ae7cfc494932da7b1dd6c8ab14c88c4b847b4ec609f74cec1e7
model-00056-of-000163.safetensors1.75 GB68130d2006590861b30611b7f6d177394136fb8b3cff7d3141bebf28e411227b
model-00057-of-000163.safetensors4.30 GB3b4826e9817a96f45f0a5af284c94791549ab681f81f2ba5db521ab15a25938e
model-00058-of-000163.safetensors4.30 GB80630144922c076d9f0a53b6cdd95d31a3578b90a05f856623afb9f57bcf13aa
model-00059-of-000163.safetensors4.30 GB432a6a2fbb10a36c309924e5129d2b95691939c2d97c5f370d482dfe10f3f7d1
model-00060-of-000163.safetensors4.30 GB59f81c7cef16c0474d9695c17bb70ad8cfd99f7213aa939964294d807922a2fb
model-00061-of-000163.safetensors4.30 GB69cde84d3893db464497ac2894ae6128f8c058fd02f74d1c23afd0a2a93e2adf
model-00062-of-000163.safetensors4.30 GB715c4c8739fff8db573dde14d77c8917b3f4eeb8fe4c20150c36459bf1b6d615
model-00063-of-000163.safetensors4.30 GBbf0f5c6e778fd299fdca261d1d2df72cbb93f1465c0de22cea2e6bbfc52554b6
model-00064-of-000163.safetensors4.30 GBd99efa8b327f7fc4929798dfa3bafd04fb5c036915919a84e268aaf25e67424d
model-00065-of-000163.safetensors4.30 GB898c045b5e0602e2a496debcec20396a824310b3107f1c4db6214ed6a3c1ac79
model-00066-of-000163.safetensors4.30 GB01e069367ad874db34873e01d75462fc2813591e9c1e7b45e54e675d29a23098
model-00067-of-000163.safetensors4.30 GBf0cbc915d403f7ae15744735b33e1ec65b53c7ebc2c2ee487481bd4fb6d111b2
model-00068-of-000163.safetensors4.30 GB2594adae97d7a675fc785745101a1d66f007b43894fddd80440ced78eaf77e98
model-00069-of-000163.safetensors4.30 GB01daa8eb84a97158ef325a1f34dbfbb29c093845b22e6dca560e4def807586df
model-00070-of-000163.safetensors4.30 GB1f0368ad214afaff4da8e61c2b84a237a91a369c3ad0d95daae38ca75b0d62b3
model-00071-of-000163.safetensors4.30 GB0cc594400988bb846804388cd6c76496bf8ed0ccf975ebe85ba00a310532a59c
model-00072-of-000163.safetensors4.30 GB6940c2e5c775b3d688aa8e6f25ffd22e40d089722c3085b5f1e0976ac23b4f9b
model-00073-of-000163.safetensors4.30 GB3fc8ab4be0f4a284849e144c07173db39f5ed8d4e4d4838f2442f3d580d0356e
model-00074-of-000163.safetensors4.30 GB9651fe2a556d41002612ecafb595fe97801e6cc2f22519ee9f64fbac9cfbc704
model-00075-of-000163.safetensors4.30 GBf74e66e34acd6e3c61d1e90bbbac335c24e510720c33e44d3516803f38a518b0
model-00076-of-000163.safetensors4.30 GB986f6a11367f1b56006a8d332c16aac4e4b81ab29d0606b5e4cb4a00a01224e4
model-00077-of-000163.safetensors4.30 GB6b0e946a0d1d06087bb470f67208f1213c2a4ce47ca6fb56b7d31df9a27e2dc3
model-00078-of-000163.safetensors1.75 GB9835f6d79440750c5cc4b90b5f8c85a0dab9fca47cb549f9daa4afe5b0641d76
model-00079-of-000163.safetensors4.30 GB8dfe2c6835455e683a9ef645217be5cc9e9a387027c1e89e443f5118a47a0303
model-00080-of-000163.safetensors4.30 GB5afc8aa8b94c7291339887605bbe3943258aaed182885603b4027225d9894bd8
model-00081-of-000163.safetensors4.30 GB757fc061d21edb638a88883046411c30d4d40f62a8f69516230e41e6b5fdafd7
model-00082-of-000163.safetensors4.30 GB0eadd45aa5afbdb3e033c0192568f2d9babe8a18fc0ce5baabe01da8f89323c4
model-00083-of-000163.safetensors4.30 GB095348fdecd55d4d4f1d16ca143bfdbdbaf68ca2da5d7cd401a2e23f44991ead
model-00084-of-000163.safetensors4.30 GBffcf0052d53fd36d1eb00b0377e297209d4f8497cd79a78c5d683e7ae6625465
model-00085-of-000163.safetensors4.30 GB7b210ddf71720212cfc0a08360c97aeff96b33e29374f661eb740eb94f06cec8
model-00086-of-000163.safetensors4.30 GB99d1090b9423edccffa3a1e5132a69cd6616a8b9064177a901a129754ce15451
model-00087-of-000163.safetensors4.30 GBb89cf8ea275ad45b5e40fa215e4aaba099209bf9ba467f978c82f26b009c73cf
model-00088-of-000163.safetensors4.30 GB7219a03969a16af8f722f5a7df6f5e2ad51e19c86fe34a2c841d2b9b0800d8f7
model-00089-of-000163.safetensors4.30 GBe57eef5e6eb8fe1616dc3414321c75b8e4e9147579a1ff0467c8fbba592f27aa
model-00090-of-000163.safetensors4.30 GBb98655409b66bc956c9ac02788d649b954b34d344dc8245eb94661b33df1c9f0
model-00091-of-000163.safetensors4.30 GBa2c5d3f066131af8c6e4e225f7bcdbb17d72f7e798492dff43ac0e73ea53363e
model-00092-of-000163.safetensors4.30 GBf9e99f4a974577f34312906924a64a500af8f6275bee21e4015eb09bbd5415a4
model-00093-of-000163.safetensors4.30 GBbc7300167ed6f5e603c43d1aa87bfa040d60a2a103ed57162ac08f682cb75974
model-00094-of-000163.safetensors4.30 GB6cb0e4055409ecc754dd058e2d350039022d43f4ac1840825a41eae71cbb1a20
model-00095-of-000163.safetensors4.30 GBf1387857bd9d101cc83527b95a9945719b0b9484d77e966c5e3d9e8272f8d89d
model-00096-of-000163.safetensors4.30 GBb58d7c50e54b8957e2b620c57016e3c6087f2eaa18f8572bdd8d3606511bb4fa
model-00097-of-000163.safetensors4.30 GBfa678aaed884639512b36c1ecd4620d01af7f45b4244d730961f4d08806207f2
model-00098-of-000163.safetensors4.30 GBa2cd517b56750d4f5791fe30b951da61a6f9235baf71811019b1c4228b5ee934
model-00099-of-000163.safetensors4.30 GB06d5aa90ee2e7cc83c42abd109f1abb92660b96abbb0514dce3f14f36b968624
model-00100-of-000163.safetensors1.75 GB90e85dc99298fe2e4933e6cbaec263c03a0cc048c2936231a920b2dfa90b8258
model-00101-of-000163.safetensors4.30 GB9976dae2a44b4407a3a39dc69104ccce67001a307b1b49e966c98ab246b371f2
model-00102-of-000163.safetensors4.30 GBcf36bd6e7a27d2f0a41f2e5387e2be53918fbfe4c886952e2ab55bd96b56c23e
model-00103-of-000163.safetensors4.30 GBf8e08c2159b56b25dbdb1800897729f5f0bc11b8c07bc660f031e4d6a9af09b8
model-00104-of-000163.safetensors4.30 GBf1bb0364aa51a804b845c28ba9a7157855ee075ef197aa58b67c6e82bf7742d5
model-00105-of-000163.safetensors4.30 GB5541411c798dbce3610e56b1a0d4c21fe8fa4cb35cb82b4c8888942305d812ba
model-00106-of-000163.safetensors4.30 GB5a2d163f3ca1eeb85e35a44ab6d162af6a6f531186b1a50221c13d2c1254c0be
model-00107-of-000163.safetensors4.30 GB5a7d97379fce8ccfaf94fb26306737d25b1e0dfb9b9a4f2c86d767a854a13b21
model-00108-of-000163.safetensors4.30 GB2813892afb5bea5b3375e03e5c2474f7828078a9e35ffdcba01a710193477ccd
model-00109-of-000163.safetensors4.30 GB70b59cb0fe6e89b982b64be838543e9387acd9d597299347e9852962f0866eed
model-00110-of-000163.safetensors4.30 GBce860b0acca56cf2903c322983e58f74829d30c26c6519f50fc8f90b9c3570d8
model-00111-of-000163.safetensors4.30 GB912c0c99c138a314070f6534af23149a84dd7eb53b419808010fe5fa0f7ed066
model-00112-of-000163.safetensors4.30 GB8d9989812d88e027e7bd02ba1d19e61fbffb40ac05a0a7775eb82335a429d457
model-00113-of-000163.safetensors4.30 GB02c14d13f644dd148d038632610e300627e4bc4b4a0f81b73c209d29c4a36f89
model-00114-of-000163.safetensors4.30 GB881e73a7117267f6d8c90fd67322970ef6bb152e792c910ecd47c137947291f5
model-00115-of-000163.safetensors4.30 GB5a66f0fde0ffcf4b69f044c8159a85171153c41327ad7ae0d9ce1054c203b505
model-00116-of-000163.safetensors4.30 GB1102daefb72e32625becfe1ad290ff818b779d73649c7ff9e315a7e2de314bd3
model-00117-of-000163.safetensors4.30 GBd92157af0d4af8ef953cf7fb6e0b38b406fb7c4b35bdab01be2a2eddf450407e
model-00118-of-000163.safetensors4.30 GBba30d60916a77c4ce013cfbbcc453377b70c2a75ef0456a4458c9ca547111993
model-00119-of-000163.safetensors4.30 GB8938205f9d550a945121f153beb9c9c8f169eafddfc56621cdb6235e011ba294
model-00120-of-000163.safetensors4.30 GB18fa9b624779af7372e26ef79096b1ca341b3ff2be616d11bc3df2cf07387a33
model-00121-of-000163.safetensors4.30 GB669570df0b213487a0f0cd1f8845fac53c9c19c942dd14d3a42c0ea97cc28c6d
model-00122-of-000163.safetensors1.75 GB9a9a82578c3a7e6bb45f36fe41e7922d777787bf45c767c02db9897b21ea8354
model-00123-of-000163.safetensors4.30 GB84723e0f5c3f520e83b75f73318f9f7ddf43702893ae138e9fc560410f674f46
model-00124-of-000163.safetensors4.30 GB01e9467b70944bb63ac108b1ec3aa0cd47d2eba55f51d12eff38948cb02e7058
model-00125-of-000163.safetensors4.30 GB562c9706e1b17d25916b4929f2210c489cf6f8b0311d087e0c851fbcddf50607
model-00126-of-000163.safetensors4.30 GB949da3c082f9aad8c2e03e7b1f26dfad76716f85696d889cd21feb8ae6818c63
model-00127-of-000163.safetensors4.30 GB8871e7ca5651392dbdd9a5e66e398c284fc1c7111d496a2143ff497fc82b7741
model-00128-of-000163.safetensors4.30 GBcb8a5a4d53a670bf283791a2f07a65ce75b6426da3d2480f8dc650124d8d0edd
model-00129-of-000163.safetensors4.30 GB9a49ccda2e63b822be58c50320b89767108c81883fc42d13d52042e2548caf53
model-00130-of-000163.safetensors4.30 GB00ceb885b7ada31e130ba2faa47ed18b1e4a3e020ed0971a49b86f02d2933aec
model-00131-of-000163.safetensors4.30 GB2af936134d19252994e75178f70d68c2381393f698224bda38af657efdcb7b94
model-00132-of-000163.safetensors4.30 GB7ceabb5bfd0b48f6617d94ed9d4b78ee037ea56c907937addad954eb98e61b6f
model-00133-of-000163.safetensors4.30 GB213c0ae67ab8576f70eb9b45430de11bd20a37044e28b1974cac58fc5d11260e
model-00134-of-000163.safetensors4.30 GBd2cd64a8c397d2e333b84f1475312245a82455d1183641936caeec6acd7794f7
model-00135-of-000163.safetensors4.30 GB4c05694e1d64f27908fb38136f8f38819ad81056e034e4075c350809be365b76
model-00136-of-000163.safetensors4.30 GBca04d3839513a925bdcf18a805ceb8b76a5d8e0adabf36f685f18f42933d7b62
model-00137-of-000163.safetensors4.30 GBc45464fc9beebb881ce5a726e8db9fb71c66c8362536866a3e4a081dce664cd6
model-00138-of-000163.safetensors4.30 GB6a1fe7da4eaa62603aa623e28bd671e2b06f6bf8aa01a39075ae07e4a1edff7a
model-00139-of-000163.safetensors4.30 GB3ffc04eb768f592e0a8126282dd2f4039713ad274acbec0afc22944d575466b3
model-00140-of-000163.safetensors4.30 GBd6ae521438d756a1effc1b2a55cce9f632fad975910f43360c86dda2775e7217
model-00141-of-000163.safetensors3.14 GB2e49bea9a5128a8d986d2fd42d79cef2997e637a7f5b58305c47ccc449620fc2
model-00142-of-000163.safetensors4.30 GBa84052a92f73718b79ed9ab697fa35608f2e4c3f2ba24b2ea075b86f5f72794d
model-00143-of-000163.safetensors4.30 GB7682d68689d9284bc18cab0d72eb2f62bacee4888f37ebe1c4c9bfece42e7c36
model-00144-of-000163.safetensors4.30 GBe44a3f3680624d3290d196eab64dfb86af8019f50bcf3a992ad7cd6638735a79
model-00145-of-000163.safetensors4.30 GBc9c978c5afe32ea1f5afc0f5f65205441a421b5eb6d1942fca8cba9e6650c224
model-00146-of-000163.safetensors4.30 GB7f2a681f4931365b40febad455f0b73179f1a26f43735f6af3dd73b1c3d6c05a
model-00147-of-000163.safetensors4.30 GB14cb65858eaf602ba8604ce2be5c74c0f94a922bb492064fc2048d7e9b6efd2a
model-00148-of-000163.safetensors4.30 GBa4185359e4e4abe44c234981089be0b2873dc1fc1b21246711873b7f18b30fe8
model-00149-of-000163.safetensors4.30 GBd9be3b4e6790c9d217e1cc8753813307c9f791b8e7f8e8c6cacdc98c08776755
model-00150-of-000163.safetensors4.30 GB90d40cf5fb984157cd322681b021c6253f125dd51c9d8b4da986c6a97552bad7
model-00151-of-000163.safetensors4.30 GB7222b3366b2793b213134c5d8caae6569a9622b6b235e54f5500a57b80bbdf9a
model-00152-of-000163.safetensors4.30 GB0654913bb563ba931d8a54a15760d3619e5e1537841717c120c0e0623d1bf4e2
model-00153-of-000163.safetensors4.30 GB4e09a5eb4e1ea762c0b9a0691763cae6141b71276e4190f55a42310d8c977dc1
model-00154-of-000163.safetensors4.30 GBffc11b87992ce2639ff28f9ff8772ccd76a59b7409e633fc1211216155af13ab
model-00155-of-000163.safetensors4.30 GBd47a88b4d7377cb4d5a5aa44943a71f5296e41dde8eeeaff40ffc7b885d07291
model-00156-of-000163.safetensors4.30 GBeeadc5eb1bd92f99c1f42f25a6d835cfb6282274b4ed23a0ed6f3ad4148beed2
model-00157-of-000163.safetensors4.30 GB8205af59d738aa2e952ba3e2eb66c5617c8884a86b931c31fd270005712d5692
model-00158-of-000163.safetensors4.30 GBc122494d667414c2cf68d7a2f0e7ffd011c6eb26bb8391afeba47932dce5a928
model-00159-of-000163.safetensors4.30 GB6e01a5c5b28be729f6d244c2a828c4427c78c3f0777cc61f61c180d185703fb2
model-00160-of-000163.safetensors5.23 GB5163fbdd76df28fade80aabc3e071f473cb33751eaf2ecb4fa3932a5d8e77609
model-00161-of-000163.safetensors4.30 GBdc4497ab378fb78f7fcebd4de0890f8f710e1409f544efe02896f4155dca9587
model-00162-of-000163.safetensors4.30 GB9c8582309da9422e3dd517fa9a1f93ce7bb88f7e4626748509a9c84ae8394c58
model-00163-of-000163.safetensors6.58 GB0a97cb51f6a9002f817b38eac66400d3b72ffbc1b2b9ae654562bba46c904f5f
model.safetensors.index.json8.90 MBa2c5d238ab1e8301a117336e9797e0d3551cb8f6dc9dc787318b23d8f54c9248
modeling_deepseek.py75.7 KBeb6d535742061cf9da7a4232ecfe2f089d5ce20080afc5d2181e9d70ec4af8a4
tokenizer.json7.85 MB621ac2e32d0dba658404412318818aaa8ce8cda492e59830109d8da6b517fb41
tokenizer_config.json3.88 KB7f1394a1791473968ebf8ca25adc2c7f4678388a85c4aff1d4cffca881828734
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
e9b33add76 pinned now manifest updated, same commit2026-11-14 21:14 UTC173 files · 689 GB
e9b33add762026-11-14 21:14 UTC173 files · 689 GB

Use it

$ fw get deepseek-ai/DeepSeek-V3-0324
# manifest sha256 7f685cc9501b… · 689 GB · 173 files
$ fw verify ./DeepSeek-V3-0324 deepseek-ai/DeepSeek-V3-0324
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/deepseek-ai/DeepSeek-V3-0324.json --dir ./DeepSeek-V3-0324 $ python3 fw.py verify ./DeepSeek-V3-0324 ./deepseek-ai__DeepSeek-V3-0324.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download deepseek-ai/DeepSeek-V3-0324 --revision e9b33add76883f293d6bf61f6bd89b497e80e335 --local-dir ./DeepSeek-V3-0324
transformersLoad the weights in Python.
import os os.environ["HF_ENDPOINT"] = "https://freeweights.allternit.com" from transformers import AutoModelForCausalLM, AutoTokenizer tok = AutoTokenizer.from_pretrained("deepseek-ai/DeepSeek-V3-0324", revision="e9b33add76883f293d6bf61f6bd89b497e80e335") model = AutoModelForCausalLM.from_pretrained("deepseek-ai/DeepSeek-V3-0324", revision="e9b33add76883f293d6bf61f6bd89b497e80e335", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve deepseek-ai/DeepSeek-V3-0324 --revision e9b33add76883f293d6bf61f6bd89b497e80e335

License

Name
MIT License
Id
MIT
Class
Permissive
Redistribution
yes
Listing
Hosted (signed)
Decided
License as declared by the publisher. No person read it. 2026-11-14
Text in
LICENSE
Text sha256
1c8f573e830ca9b3ebfeb7ace1823146e22b66f99ee223840e7637c9e745e1c7
Terms gate
No extra terms beyond the license.

Read the license text

Licenses are checked against the license table. A custom license passes only after a person reads it.

Provenance

From: deepseek-ai <huggingface.co/deepseek-ai>Newsgroups: alt.freeweights.deepseekSubject: DeepSeek-V3-0324Date: 2026-11-14Commit: e9b33adSigned: 2DC28CC7B26A283B ✓
Upstream
deepseek-ai/DeepSeek-V3-0324
Pinned commit
e9b33add76883f293d6bf61f6bd89b497e80e335
Manifest
DeepSeek-V3-0324.json · .minisig
Manifest sha256
7f685cc9501bc7acc675f165a43b91ed977bbd4af85e78a33ff9bcfc69e6ab5f
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-14 21:14 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/deepseek-ai/DeepSeek-V3-0324.json $ curl -O https://freeweights.allternit.com/manifests/deepseek-ai/DeepSeek-V3-0324.json.minisig $ minisign -Vm DeepSeek-V3-0324.json -P RWQ7KGqyx4zCLXtUFOqvfv8L3g+8fpKJ1FsuxPyOYMF+4KufbUxKq1Oq $ shasum -a 256 <file> # compare with the Files tab

A manifest whose signature fails must be rejected. A file whose size or sha256 does not match must be discarded. Verify a download

Model tree

4 models in the catalog name this one as their parent.

Quantizations
4
Get it
Download
$ HF_ENDPOINT=https://freeweights.allternit.com hf download deepseek-ai/DeepSeek-V3-0324
Open in Freeweights Studio

Pull, verify and run it in the Allternit app on Desktop, web or phone.

Signed manifest
minisign, key 2DC28CC7B26A283B. DeepSeek-V3-0324.json. Provenance. Takedown history: none.

Variants

4 quantized or adapter builds of DeepSeek-V3-0324. Each has its own license check and page.

From: timm <huggingface.co/timm>Subject: deepseek_vit_412m.deepseek_v4_1_flash
From: bartowski <huggingface.co/bartowski>Subject: deepseek-ai_DeepSeek-R1-0528-GGUF
From: bartowski <huggingface.co/bartowski>Subject: deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-GGUF
From: bartowski <huggingface.co/bartowski>Subject: deepseek-ai_DeepSeek-V3-0324-GGUF
From: bartowski <huggingface.co/bartowski>Subject: deepseek-ai_DeepSeek-V3.1-GGUF
From: mlx-community <huggingface.co/mlx-community>Subject: deepseek-ai-DeepSeek-V4-Flash-8bit